© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19856
    Prev
    Next
    INDEX
    Explanations

    true else false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¦Ĥæŀľä¸Ģ个
    -0.07
    ONGL
    -0.06
    lin
    -0.06
    INSTANCE
    -0.06
    ervas
    -0.06
    大åıij
    -0.06
    istle
    -0.06
    çŁ¥éģĵèĩªå·±
    -0.06
    las
    -0.06
    ilig
    -0.06
    POSITIVE LOGITS
    è°ĥåĴĮ
    0.05
    ÑĤва
    0.05
    éĢıäºĨ
    0.05
    è¢Ĵ
    0.05
     sharper
    0.05
    ä¸į好äºĨ
    0.05
    ä¸įåĢĴ
    0.05
     KH
    0.05
    irts
    0.05
    æĥħçļĦ
    0.05
    Activations Density 0.030%

    No Known Activations